Dynamic Pulmonary Trunk Modeling in Computed Tomography and Magnetic Resonance Imaging Based on the Detection of Bounding Boxes, Anatomical Landmarks, and Ribs of a Pulmonary Artery

1. A method for generating a pulmonary trunk model from 4D cardiac image data, comprising: receiving 4D cardiac image data comprising a plurality of frames, each frame comprising volumetric image data; detecting bounding boxes in the frames of the 4D cardiac image data; detecting anatomic landmarks in the frames of the 4D cardiac image data based on the detected bounding boxes; detecting ribs of a pulmonary artery in the frames of the 4D cardiac image data based on the detected anatomic landmarks; and generating a dynamic pulmonary trunk model by fitting a physiological pulmonary trunk model to the frames of the 4D cardiac image data based on the detected ribs and anatomic landmarks.

2. The method of claim 1 , wherein said 4D cardiac image data is 4D computed tomography (CT) sequence.

3. The method of claim 2 , wherein: said step of detecting bounding boxes comprises detecting bounding boxes in frames of the 4D CT sequence representing end-diastolic (ED) and end-systolic (ES) phases of a cardiac cycle and extending the detected bounding boxes to remaining frames of the 4D CT sequence; said step of detecting anatomic landmarks comprises detecting anatomic landmarks in the frames of the 4D CT sequence representing the ED and ES phases and extending the detected anatomic landmarks to the remaining frames of the 4D CT sequence; said step of detecting ribs comprises detecting ribs of the pulmonary artery in the frames of the 4D CT sequence representing the ED and ES phases and extending the detected ribs to the remaining frames of the 4D CT sequence; and said step of generating a dynamic pulmonary trunk model comprises fitting the physiological pulmonary trunk model to frames of the 4D CT sequence representing the ED and ES phases and extending the physiological pulmonary trunk model to the remaining frames of the 4D CT sequence.

4. The method of claim 1 , wherein said 4D cardiac image data is MRI data comprising volumetric frames and frames having 2D + t projections.

5. The method of claim 4 , wherein said steps of detecting bounding boxes, detecting anatomic landmarks, detecting ribs, and generating a dynamic pulmonary trunk model are performed on the volumetric frames of the MRI data, and the generated dynamic pulmonary trunk model is propagated to the frames having 2D + t projections.

6. The method of claim 1 , wherein said step of detecting bounding boxes comprises: detecting a bounding box at a right ventricular outflow tract (RVOT) region and a bounding box at a bifurcation region in the frames of the 4D cardiac data.

7. The method of claim 6 , wherein said step of detecting a bounding box at an RVOT region and a bounding box at a bifurcation region in the frames of the 4D cardiac data comprises: detecting the bounding box at the RVOT region and the bounding box at the bifurcation region using trained detectors for each bounding box, wherein the trained detectors are trained using probabilistic boosting tree (PBT) with Haar features.

8. The method of claim 6 , wherein said step of detecting anatomic landmarks comprises: detecting trigone and RVOT locations in the frames of the 4D cardiac data based on the detected RVOT region bounding box, and main-bifurcation, left-bifurcation, and right-bifurcation locations in the 4D cardiac data based on the detected bifurcation bounding box.

9. The method of claim 8 , wherein said step of detecting trigone and RVOT locations in the frames of the 4D cardiac data based on the detected RVOT region bounding box, and main-bifurcation, left-bifurcation, and right-bifurcation locations based on the detected bifurcation bounding box comprises: detecting the trigone, RVOT, main-bifurcation, left-bifurcation, and right-bifurcation locations using trained detectors for each anatomic landmark, wherein the trained detectors are trained using a probabilistic boosting tree (PBT) with Haar features.

10. The method of claim 8 , wherein said step of detecting ribs of a pulmonary artery comprises: detecting a main-rib based on the detected RVOT and main-bifurcation locations, a left-rib based on the detected main-bifurcation and left-bifurcation locations, and a right-rib based on the detected main-bifurcation and right bifurcation locations.

11. The method of claim 10 , wherein said step of detecting a main-rib based on the detected RVOT and main-bifurcation locations, a left-rib based on the detected main-bifurcation and left-bifurcation locations, and a right-rib based on the detected main-bifurcation and right bifurcation locations comprises: detecting the main-rib, left-rib, and right rib with trained circle detectors for each rib.

12. The method of claim 1 , wherein said step of generating a dynamic pulmonary trunk model comprises: generating an initial estimate of the pulmonary trunk model in the frames of the 4D cardiac image data by fitting the physiological pulmonary trunk model based on the detected ribs and anatomic features; and detecting a boundary of the pulmonary trunk in the frames of the 4D image data to refine a boundary of the initial estimate of the pulmonary trunk model.

13. The method of claim 12 , wherein said step of detecting a boundary of the pulmonary trunk in the frames of the 4D image data comprises: detecting the boundary of the pulmonary trunk using a trained boundary detector, wherein the trained boundary detector is trained using probabilistic boosting tree (PBT) with steerable features.

14. The method of claim 1 , further comprising: quantitatively evaluating the pulmonary trunk using the generated dynamic pulmonary trunk model.

15. An apparatus for generating a pulmonary trunk model from 4D cardiac image data, comprising: means for receiving 4D cardiac image data comprising a plurality of frames, each frame comprising volumetric image data; means for detecting bounding boxes in the frames of the 4D cardiac image data; means for detecting anatomic landmarks in the frames of the 4D cardiac image data based on the detected bounding boxes; means for detecting ribs of a pulmonary artery in the frames of the 4D cardiac image data based on the detected anatomic landmarks; and means for generating a dynamic pulmonary trunk model by fitting a physiological pulmonary trunk model to the frames of the 4D cardiac image data based on the detected ribs and anatomic landmarks.

16. The apparatus of claim 15 , wherein said means for detecting bounding boxes comprises: means for detecting a bounding box at a right ventricular outflow tract (RVOT) region and a bounding box at a bifurcation region in the frames of the 4D cardiac data.

17. The apparatus of claim 16 , wherein said means for detecting anatomic landmarks comprises: means for detecting trigone and RVOT locations in the frames of the 4D cardiac data based on the detected RVOT region bounding box, and main-bifurcation, left-bifurcation, and right-bifurcation locations in the 4D cardiac data based on the detected bifurcation bounding box.

18. The apparatus of claim 17 , wherein said means for detecting ribs of a pulmonary artery comprises: means for detecting a main-rib based on the detected RVOT and main-bifurcation locations, a left-rib based on the detected main-bifurcation and left-bifurcation locations, and a right-rib based on the detected main-bifurcation and right bifurcation locations.

19. The apparatus of claim 15 , wherein said means for generating a dynamic pulmonary trunk model comprises: means for generating an initial estimate of the pulmonary trunk model in the frames of the 4D cardiac image data by fitting the physiological pulmonary trunk model based on the detected ribs and anatomic features; and means for detecting a boundary of the pulmonary trunk in the frames of the 4D image data to refine a boundary of the initial estimate of the pulmonary trunk model.

20. The apparatus of claim 15 , further comprising: means for quantitatively evaluating the pulmonary trunk using the generated dynamic pulmonary trunk model.

21. A non-transitory computer readable medium encoded with computer executable instructions for generating a pulmonary trunk model from 4D cardiac image data, the computer executable instructions defining steps comprising: receiving 4D cardiac image data comprising a plurality of frames, each frame comprising volumetric image data; detecting bounding boxes in the frames of the 4D cardiac image data; detecting anatomic landmarks in the frames of the 4D cardiac image data based on the detected bounding boxes; detecting ribs of a pulmonary artery in the frames of the 4D cardiac image data based on the detected anatomic landmarks; and generating a dynamic pulmonary trunk model by fitting a physiological pulmonary trunk model to the frames of the 4D cardiac image data based on the detected ribs and anatomic landmarks.

22. The non-transitory computer readable medium of claim 21 , wherein the computer executable instructions defining the step of detecting bounding boxes comprise computer executable instructions defining the step of: detecting a bounding box at a right ventricular outflow tract (RVOT) region and a bounding box at a bifurcation region in the frames of the 4D cardiac data.

23. The non-transitory computer readable medium of claim 22 , wherein the computer executable instructions defining the step of detecting anatomic landmarks comprise computer executable instructions defining the step of: detecting trigone and RVOT locations in the frames of the 4D cardiac data based on the detected RVOT region bounding box, and main-bifurcation, left-bifurcation, and right-bifurcation locations in the 4D cardiac data based on the detected bifurcation bounding box.

24. The non-transitory computer readable medium of claim 23 , wherein the computer executable instructions defining the step of detecting ribs of a pulmonary artery comprise computer executable instructions defining the step of: detecting a main-rib based on the detected RVOT and main-bifurcation locations, a left-rib based on the detected main-bifurcation and left-bifurcation locations, and a right-rib based on the detected main-bifurcation and right bifurcation locations.

25. The non-transitory computer readable medium of claim 21 , wherein said the computer executable instructions defining the step of generating a dynamic pulmonary trunk model comprise computer executable instructions defining the steps of: generating an initial estimate of the pulmonary trunk model in the frames of the 4D cardiac image data by fitting the physiological pulmonary trunk model based on the detected ribs and anatomic features; and detecting a boundary of the pulmonary trunk in the frames of the 4D image data to refine a boundary of the initial estimate of the pulmonary trunk model.

26. The non-transitory computer readable medium of claim 21 , further comprising computer executable instructions defining the step of: quantitatively evaluating the pulmonary trunk using the generated dynamic pulmonary trunk model.